session_checkpoint

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly reveals the side effects: it writes several specific files and auto-writes handoff.md to CLAUDE.md so the next session loads it. This gives an agent a solid mental model of what the call does to disk, even without a dedicated effects section.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is tight and front-loaded: a one-line purpose, a prominent usage directive, and a compact file list. Every sentence contributes, and the critical 'CALL THIS at 70-80% context' guidance appears near the beginning rather than buried. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the essential call rationale, the exact persistence artifacts, and a key auto-write side effect. A small gap is that it does not state what the tool returns or whether files are overwritten, but the listed outputs and input schema already give enough context for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is moderate: one_liner and context_pct are described in the input schema, while trigger has only an enum/default. The description adds a little context-pct meaning via the '70-80% context' guidance, but it does not explain trigger values or elaborate on one_liner usage beyond the schema. It mostly relies on the schema for parameter meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Save'), a clear resource ('current session state to disk'), and enumerates the exact files written, making its purpose unmistakable. It also distinguishes itself from sibing tools like session_search or session_status by emphasizing a full persistent dump rather than inspection or incremental update.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells the agent when to call this: 'CALL THIS at 70-80% context'. This is a concrete trigger condition. It does not, however, contrast this tool with session_update or session_log, so exclusions and alternatives are left implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.